© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1777
    Prev
    Next
    INDEX
    Explanations

    [techniques] => [techniques]

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     techniques
    -19.38
     technique
    -18.75
     Techniques
    -17.88
     society
    -17.63
     Technique
    -17.00
    姜
    -16.88
    药物
    -16.00
    天气
    -15.75
    speaker
    -15.38
    NETWORK
    -14.81
    POSITIVE LOGITS
    写字
    21.50
    ball
    19.63
    balls
    19.38
     ball
    19.25
    球
    18.88
     balls
    18.25
    电脑
    17.63
     computer
    17.13
     Computer
    17.00
    .arc
    17.00
    Activations Density 0.224%

    No Known Activations